I am a fourth-year PhD candidate with the Institute for IT Security at University of Luebeck, advised by Esfandiar Mohammadi. My main interests are differential privacy and machine learning. I want to improve the utility-privacy trade-offs of algorithms.
Outside of work, I enjoy spending time with my wife, working out and spending time outdoors with my dog.
MammothDP: Differentially Private Boosted Decision Trees, hyperparameter-free and ready for Trusted Hardware
Moritz Kirschte, Thorsten Peinemann, Kari Kostiainen, Jan Wichelmann, Thomas Eisenbarth, Esfandiar Mohammadi
In Submission. [PDF]
S-BDT: Distributed Differentially Private Gradient Boosted Decision Trees
Thorsten Peinemann*, Moritz Kirschte*, Joshua Stock, Carlos Cotrini, Esfandiar Mohammadi
*The first two authors equally contributed to this work.
CCS 2024 [PDF] [Code]
Email: t.peinemann@uni-luebeck.de
LinkedIn: Thorsten Peinemann